173 citations · 876 across the 56 of their papers we have counts for
5 papers · 1 filter
Policies Modulating Trajectory Generators
Atil Iscen, Ken Caluwaerts, Jie Tan +4
We propose an architecture for learning complex controllable behaviors by having simple Policies Modulate Trajectory Generators (PMTG), a powerful combination that can provide both…
Learning Stabilizable Nonlinear Dynamics with Contraction-Based Regularization
Sumeet Singh, Spencer M. Richards, Vikas Sindhwani +2
We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics. The key contribution is a control-theoretic regularizer…
Data Efficient Reinforcement Learning for Legged Robots
Yuxiang Yang, Ken Caluwaerts, Atil Iscen +3
We present a model-based framework for robot locomotion that achieves walking based on only 4.5 minutes (45,000 control steps) of data collected on a quadruped robot. To accurately…
Teleoperator Imitation with Continuous-time Safety
Bachir El Khadir, Jake Varley, Vikas Sindhwani
Learning to effectively imitate human teleoperators, with generalization to unseen and dynamic environments, is a promising path to greater autonomy enabling robots to steadily acq…
Provably Robust Blackbox Optimization for Reinforcement Learning
Krzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder +6
Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they…